Instructions to use Mit1208/Florence-2-DocLayNet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mit1208/Florence-2-DocLayNet with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="Mit1208/Florence-2-DocLayNet", trust_remote_code=True)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Mit1208/Florence-2-DocLayNet", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("Mit1208/Florence-2-DocLayNet", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Mit1208/Florence-2-DocLayNet with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mit1208/Florence-2-DocLayNet"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mit1208/Florence-2-DocLayNet",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Mit1208/Florence-2-DocLayNet

SGLang

How to use Mit1208/Florence-2-DocLayNet with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Mit1208/Florence-2-DocLayNet" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mit1208/Florence-2-DocLayNet",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Mit1208/Florence-2-DocLayNet" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mit1208/Florence-2-DocLayNet",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Mit1208/Florence-2-DocLayNet with Docker Model Runner:
```
docker model run hf.co/Mit1208/Florence-2-DocLayNet
```

Florence-2-DocLayNet / README.md

Mit1208

Update README.md

b57f5ff verified about 2 years ago

preview code

Raw

History Blame Contribute Delete

3.22 kB

	---
	library_name: transformers
	license: mit
	datasets:
	- pierreguillou/DocLayNet-small
	language:
	- en
	pipeline_tag: image-text-to-text
	---

	# Model Card for Model ID

	<!-- Provide a quick summary of what the model is/does. -->



	## Model Details

	### Model Description

	<!-- Provide a longer summary of what this model is. -->

	This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

	- Developed by: [Mit Patel]
	- Shared by [optional]: [Mit Patel]
	- Finetuned from model [optional]: https://huggingface.co/microsoft/Florence-2-base-ft

	### Recommendations

	<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

	Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

	## How to Get Started with the Model

	Use the code below to get started with the model.

	[More Information Needed]

	## Training Details

	### Training Data

	<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

	[More Information Needed]

	### Inference Procedure

	```python

	!pip install -qU transformers
	!pip install -qU accelerate bitsandbytes einops flash_attn timm
	!pip install -q datasets

	from PIL import Image
	import requests
	import torch
	from transformers import AutoProcessor, AutoModelForVision2Seq, BitsAndBytesConfig, TrainingArguments, AutoModelForCausalLM
	import requests
	import re
	from transformers import AutoConfig, AutoProcessor, AutoModelForCausalLM

	base_model = AutoModelForCausalLM.from_pretrained("microsoft/Florence-2-base-ft", trust_remote_code=True,)
	processor = AutoProcessor.from_pretrained("microsoft/Florence-2-base-ft", trust_remote_code=True,)
	model = AutoModelForCausalLM.from_pretrained("Mit1208/Florence-2-DocLayNet", trust_remote_code=True, config = base_model.config)

	def run_example(task_prompt, image, text_input=None):
	if text_input is None:
	prompt = task_prompt
	else:
	prompt = task_prompt + text_input
	print(prompt)
	inputs = processor(text=prompt, images=image, return_tensors="pt").to(device)
	generated_ids = model.generate(
	input_ids=inputs["input_ids"],
	pixel_values=inputs["pixel_values"],
	max_new_tokens=1024,
	early_stopping=False,
	do_sample=False,
	num_beams=3,
	)
	generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]
	print(generated_text)
	parsed_answer = processor.post_process_generation(
	generated_text,
	task=task_prompt,
	image_size=(image.width, image.height)
	)

	return parsed_answer

	from PIL import Image
	import requests

	image = Image.open('form-1.png').convert('RGB')
	task_prompt = '<OD>'
	results = run_example(task_prompt, example['image'].resize(size=(1000, 1000)))
	print(results)

	```

	<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->